2D AI AOI Equipment Achieves Remarkable Results in Paper Defect Detection

In the chemical/material industry, paper quality inspection is crucial. WeLinkirt's 2D AI AOI equipment provides an efficient solution for paper defect detection with its advanced technology.

User Scenario: A leading manufacturer in the chemical/material industry. In the finished-product inspection process of its paper production line, the main products are various industrial papers and packaging papers. The detection objects are surface defects of the paper, such as holes, scratches, stains, and wrinkles.

Pain Points: Traditional paper defect detection methods mainly rely on manual visual inspection and simple optical detection equipment. Manual visual inspection is inefficient and easily affected by factors such as fatigue and inattention, with a miss-detection rate as high as 5%, and the labor cost is also relatively high. Simple optical detection equipment has a false-alarm rate of 30%, requiring a large amount of manual re-inspection, which increases time and labor costs. Meanwhile, as the application of industrial AI in the manufacturing industry deepens, the manufacturer also hopes to introduce more advanced technologies to activate new applications of industrial vision quality inspection and improve production efficiency and product quality.

Technical Principle

WeLinkirt's 2D AI AOI equipment uses high-resolution 2D imaging technology, which can clearly capture the tiny details on the paper surface. Its imaging principle is based on advanced optical sensors and image-processing algorithms. Through precise control of light and image enhancement processing, the clarity and contrast of the image are improved. During the detection process, the equipment uses a deep-learning secondary image-judging algorithm to analyze the collected images. Through a large number of sample trainings, this algorithm can accurately identify various types of defects, classify and locate them. The semantic false-alarm filtering function further improves the detection accuracy. It analyzes the semantic features of defects and filters out false alarms caused by factors such as paper texture and illumination changes.

• High - resolution 2D imaging: It can capture micron-level defects, providing accurate data for subsequent analysis.
• Deep - learning secondary image-judging: By learning from a large number of samples, the detection model is continuously optimized to improve the accuracy and stability of detection.
• Semantic false-alarm filtering: It reduces false alarms caused by environmental factors and the paper's own characteristics, improving detection efficiency.

WeLinkirt's Solution and Product

Centered on the 2D AI AOI equipment, WeLinkirt provides a complete paper defect detection solution. This equipment can achieve high-speed online full inspection, detecting thousands of sheets of paper per hour, meeting the needs of large-scale production. At the same time, the equipment has a micron-level detection accuracy, capable of detecting tiny defects to ensure product quality. In the implementation process, in combination with the DaoAI AI AOI software system, using its feature-recognition ability of the visual basic model, with only 1-20 good samples, 0-code automatic programming can be realized in 5 minutes, greatly shortening the change-over time.

The 2D AI AOI equipment provides an efficient and accurate solution for paper defect detection.

Quantitative Results: After using the 2D AI AOI equipment, the detection rate of paper defects reaches 98%, and the miss-detection rate is reduced to <2%, greatly improving product quality. The false-alarm rate is reduced by -75%, reducing the workload of manual re-inspection. The change-over time is shortened from the original 30 minutes to 5min, improving production efficiency.